kernel:Kernel panic - not syncing: Fatal exception in interrupt

[netrik]

root@servm1:~# pveversion -v
pve-manager: 2.3-13 (pve-manager/2.3/7946f1f1)
running kernel: 2.6.32-18-pve
proxmox-ve-2.6.32: 2.3-88
pve-kernel-2.6.32-16-pve: 2.6.32-82
pve-kernel-2.6.32-18-pve: 2.6.32-88
lvm2: 2.02.95-1pve2
clvm: 2.02.95-1pve2
corosync-pve: 1.4.4-4
openais-pve: 1.1.4-2
libqb: 0.10.1-2
redhat-cluster-pve: 3.1.93-2
resource-agents-pve: 3.9.2-3
fence-agents-pve: 3.1.9-1
pve-cluster: 1.0-36
qemu-server: 2.3-17
pve-firmware: 1.0-21
libpve-common-perl: 1.0-48
libpve-access-control: 1.0-26
libpve-storage-perl: 2.3-6
vncterm: 1.0-3
vzctl: 4.0-1pve2
vzprocps: 2.0.11-2
vzquota: 3.1-1
pve-qemu-kvm: 1.4-6
ksm-control-daemon: 1.1-1

we are still having the same problem as explained in this thread http://forum.proxmox.com/threads/13650-Proxmox-cluster-over-Infiniband-issues
the only error we are seeing is "kernel:Kernel panic - not syncing: Fatal exception in interrupt" for the rest nothing in the logs
this happens on the node where we are running a KVM with a particular backup script generating some load, the node will lock up completely and be fenced
we have the problem almost on a daily basis

It looks very much like we encounter the same problem like here

http://forum.proxmox.com/threads/13333-2-6-32-19-pve-lock-up-problem-when-using-Infiniband

 

[dietmar]

Do you use a separate network for cluster communication? Else, try to reduce/limit backup traffic.

 

[netrik]

Do you use a separate network for cluster communication? Else, try to reduce/limit backup traffic.

Hi Dietmar,

the script generates around 80 Mbit of traffic on a 20 Gbit infiniband network with no congestion. I have multicast en unicast ping scripts running to that node and I can see that it just completely locks up and generates a kernel panic . To me it looks like we encounter the same bug that e100 encountered. You posted a link to another kernel in his thread

 

[e100]

I have not had any issues since I updated to the test kernel that was provided in the other thread.
The current release 2.6.32-19-pve kernel seems ok too, have 23 nodes running it with no problems.

Have you tried updating to the latest kernel?